Christina Testa Marques, R. S. Bôaventura, Keiji Yamanaka
{"title":"TÉCNICA REDES NEURAIS ARTIFICIAIS APLICADA NA DETECÇÃO DE ATRITO COM CLIENTES E OPORTUNIDADES DE NOVOS NEGÓCIOS","authors":"Christina Testa Marques, R. S. Bôaventura, Keiji Yamanaka","doi":"10.37423/211004894","DOIUrl":null,"url":null,"abstract":"The proposed system can detect the concern with customers before losing them, aiming at the growth and sustainability of the company. This study aims proposes to classify the company's customers into groups with similar profiles. This will allow the company to offer new products to customers in accordance with to the features listed in the group and avoid evasion The proposed system was developed using the technology of artificial neural network model using the Self Organizing Maps network . The neural network model has 55 entries withdrawn from a database composed of 500 customers. 1","PeriodicalId":149300,"journal":{"name":"Engenharia: a máquina que constrói o futuro","volume":"57 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engenharia: a máquina que constrói o futuro","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.37423/211004894","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The proposed system can detect the concern with customers before losing them, aiming at the growth and sustainability of the company. This study aims proposes to classify the company's customers into groups with similar profiles. This will allow the company to offer new products to customers in accordance with to the features listed in the group and avoid evasion The proposed system was developed using the technology of artificial neural network model using the Self Organizing Maps network . The neural network model has 55 entries withdrawn from a database composed of 500 customers. 1